Add image index and pdf parse (#3956)

* feat: think tag parse

* feat: parse think tag test

* feat: pdf parse ux

* feat: doc2x parse

* perf: rewrite training mode setting

* feat: image parse queue

* perf: image index

* feat: image parse process

* feat: add init sh

* fix: ts

packages/global/common/string/markdown.ts

@@ -1,4 +1,4 @@
-import { batchRun } from '../fn/utils';
+import { batchRun } from '../system/utils';
 import { getNanoid, simpleText } from './tools';
 import type { ImageType } from '../../../service/worker/readFile/type';
 
@@ -37,6 +37,80 @@ export const simpleMarkdownText = (rawText: string) => {
   return rawText.trim();
 };
 
+export const htmlTable2Md = (content: string): string => {
+  return content.replace(/<table>[\s\S]*?<\/table>/g, (htmlTable) => {
+    try {
+      // Clean up whitespace and newlines
+      const cleanHtml = htmlTable.replace(/\n\s*/g, '');
+      const rows = cleanHtml.match(/<tr>(.*?)<\/tr>/g);
+      if (!rows) return htmlTable;
+
+      // Parse table data
+      let tableData: string[][] = [];
+      let maxColumns = 0;
+
+      // Try to convert to markdown table
+      rows.forEach((row, rowIndex) => {
+        if (!tableData[rowIndex]) {
+          tableData[rowIndex] = [];
+        }
+        let colIndex = 0;
+        const cells = row.match(/<td.*?>(.*?)<\/td>/g) || [];
+
+        cells.forEach((cell) => {
+          while (tableData[rowIndex][colIndex]) {
+            colIndex++;
+          }
+          const colspan = parseInt(cell.match(/colspan="(\d+)"/)?.[1] || '1');
+          const rowspan = parseInt(cell.match(/rowspan="(\d+)"/)?.[1] || '1');
+          const content = cell.replace(/<td.*?>|<\/td>/g, '').trim();
+
+          for (let i = 0; i < rowspan; i++) {
+            for (let j = 0; j < colspan; j++) {
+              if (!tableData[rowIndex + i]) {
+                tableData[rowIndex + i] = [];
+              }
+              tableData[rowIndex + i][colIndex + j] = i === 0 && j === 0 ? content : '^^';
+            }
+          }
+          colIndex += colspan;
+          maxColumns = Math.max(maxColumns, colIndex);
+        });
+
+        for (let i = 0; i < maxColumns; i++) {
+          if (!tableData[rowIndex][i]) {
+            tableData[rowIndex][i] = ' ';
+          }
+        }
+      });
+      const chunks: string[] = [];
+
+      const headerCells = tableData[0]
+        .slice(0, maxColumns)
+        .map((cell) => (cell === '^^' ? ' ' : cell || ' '));
+      const headerRow = '| ' + headerCells.join(' | ') + ' |';
+      chunks.push(headerRow);
+
+      const separator = '| ' + Array(headerCells.length).fill('---').join(' | ') + ' |';
+      chunks.push(separator);
+
+      tableData.slice(1).forEach((row) => {
+        const paddedRow = row
+          .slice(0, maxColumns)
+          .map((cell) => (cell === '^^' ? ' ' : cell || ' '));
+        while (paddedRow.length < maxColumns) {
+          paddedRow.push(' ');
+        }
+        chunks.push('| ' + paddedRow.join(' | ') + ' |');
+      });
+
+      return chunks.join('\n');
+    } catch (error) {
+      return htmlTable;
+    }
+  });
+};
+
 /**
  * format markdown
  * 1. upload base64